I'm sorry to bring this up, but it's very important for me to solve this problem. I run the conv_net_train.py and the following error occurs:
MemoryError:
Apply node that caused the error: AdvancedSubtensor1(Words, Elemwise{Cast{int32}}.0)
Toposort index: 77
Inputs types: [TensorType(float64, matrix), TensorType(int32, vector)]
Inputs shapes: [(30392, 300), (2386800,)]
Inputs strides: [(2400, 8), (4,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Reshape{4}(AdvancedSubtensor1.0, MakeVector{dtype='int64'}.0)]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "conv_net_train.py", line 510, in
activations=[Sigmoid])
File "conv_net_train.py", line 113, in train_conv_net
layer0_input = Words[T.cast(x.flatten(), dtype="int32")].reshape(
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
I'm sorry to bring this up, but it's very important for me to solve this problem. I run the conv_net_train.py and the following error occurs: MemoryError: Apply node that caused the error: AdvancedSubtensor1(Words, Elemwise{Cast{int32}}.0) Toposort index: 77 Inputs types: [TensorType(float64, matrix), TensorType(int32, vector)] Inputs shapes: [(30392, 300), (2386800,)] Inputs strides: [(2400, 8), (4,)] Inputs values: ['not shown', 'not shown'] Outputs clients: [[Reshape{4}(AdvancedSubtensor1.0, MakeVector{dtype='int64'}.0)]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer): File "conv_net_train.py", line 510, in
activations=[Sigmoid])
File "conv_net_train.py", line 113, in train_conv_net
layer0_input = Words[T.cast(x.flatten(), dtype="int32")].reshape(
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.